End User
SWW
Description
The AI-Enhanced Model Predictive Control service extends the hybrid modelling approach of Service 8 with a forward-looking optimisation component. By forecasting grid states over a short prediction horizon and evaluating different configurations of controllable assets (batteries, curtailable generators, flexible loads) through repeated PowerFactory simulations, the service identifies the asset configuration that best stabilises the grid. All recommendations are presented to the operator for final decision — automated intervention is explicitly not foreseen.
Core Capabilities
Predictive & Prescriptive Analytics
Optimization & Decision Support
Business Need
Controllable assets in the distribution grid can proactively prevent voltage deviations and thermal constraint violations — but their effective use requires reliable short-term grid state forecasts and systematic evaluation of control options. Without this forward-looking capability, operators react to grid stress events rather than preventing them, limiting the value of invested flexibility resources.
Key Performance Indicators
Forecast quality of load/generation predictions at specific nodes
Effectiveness of optimisation recommendations vs. actual grid state materialised
Identification and documentation of systematic forecasting weaknesses
Computational performance for operational decision-making timelines
Data Provided
Recommended controllable asset configurations (battery dispatch, feed-in curtailment) per time step across prediction horizon
Anticipated grid state under recommended configuration
Inputs: hybrid PowerFactory model (from Service 8), time-series load/generation forecasts, controllable asset parameters
TEF
TEF DSO